THE 3 rd INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
174
Speed: Because it can anticipate objects in real-time, this approach
enhances detection speed.
High accuracy: YOLO is a prediction strategy that yields accurate
findings while minimizing background mistakes.
Learning capabilities: The method has great learning capabilities, allowing
it to learn object representations and apply them to object detection.
I utilize a Raspberry Pi 4 Model B as a mobile platform. The Raspberry
Pi is a single-board computer, which means that the microprocessor, memory,
wireless radios, and ports are all positioned on a single board. Because the
Pi is a Linux computer, it can technically do all of the functions of a Linux
computer and being used for OBJECT DETECTION. Unlike most computers
that have a built-in hard drive or SSD storage option, the Pi's operating
system is loaded on a microSD card, which is also where you'll save all of
your data because the board lacks any built-in storage. As the hardware part
of our object detector, we used a Raspberry Pi 4 Model B and a Raspberry
Pi Camera. We'll also need a microSD card with at least 32GB of storage
space because creating OpenCV may be a memory-intensive process.
You only look once (YOLO) model results (Figure 1):
References: [1] https://www.pyimagesearch.com/2020/01/27/yolo-and-tiny-yolo-object-detection-on-the-
raspberry-pi-and-movidius-ncs/
[2] https://medium.datadriveninvestor.com/object-detection-with-raspberry-pi-and-python-
bc6b3a1d4972
[3] Albawi, Saad & Abed Mohammed, Tareq & ALZAWI, Saad. (2017). Understanding of a
Convolutional Neural Network. 10.1109/ICEngTechnol.2017.8308186.
[4] A. F. Joseph Redmon, "YOLOv3: An Incremental Improvement," University of Washington,
2018.